Does this MCP just list tasks, or does it create a plan?

It does more than list tasks. It creates a structured, hierarchical plan. It breaks the goal down into subtasks and leaf actions, giving you a true roadmap, not just a checklist.

What happens if my plan has a logical error?

You use the validate_dependencies capability. This checks for circular references, which are logical loops. If a loop exists, the MCP flags it, preventing your agent from getting stuck in a planning cycle.

Can I use this for non-project goals?

Yes. While it's built for planning, it works on any high-level objective. Whether it's writing a book or planning a trip, it forces the goal into a structured, actionable format.

Is the complexity score useful?

The complexity score is a metric that quantifies the difficulty of the task tree. It helps you understand the overall effort required and how many parts can be worked on at the same time.

How is task complexity calculated?

Complexity is a weighted sum of word count, domain specificity, and ambiguity, which is then scaled by the decomposition depth.

What happens if a task is too ambiguous?

If the ambiguity score exceeds 0.8, the decompose_task capability will flag the task as too vague for reliable decomposition.

Can I detect circular dependencies between tasks?

Yes, you can use the validate_dependencies capability to ensure your task hierarchy does not contain logical loops.

An astronaut overseeing a futuristic data hub

Download PDF Markdown Version

Connect Agent Task Decomposition Engine to your AI

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Give your AI agent a reliable, structured plan every time.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 3 capabilities

We ship only the actions that matter.

Capability set01 / 01

01-03

3 capabilities in this set.

Part of 3 available through Agent Task Decomposition Engine.

01
Analyze complexity
Calculate the structural metrics of a previously decomposed task tree. This capability gives you a complexity score and estimates how many tasks can run at the same time.
02
Decompose task
Break a high-level task into a hierarchical structure of subtasks and leaf actions. Give it a goal, and it returns a structured plan.
03
Validate dependencies
Check the task decomposition to ensure there are no logical loops or circular references. This prevents your agent from getting stuck in a planning cycle.

Real work

What teams actually run

Marketing Campaign Planning

Give the agent the goal 'Launch a new product line.' The MCP breaks it into market research, creative assets, and channel selection, giving you a full roadmap.

Software Development Sprints

Use it to take a feature request and decompose it into specific, ordered tickets, ensuring no critical step is missed.

Academic Research Project

Feed the agent a thesis topic. The MCP structures the work into literature review, methodology design, and writing phases, keeping the plan linear.

Event Coordination

Plan a multi-day conference. The MCP breaks the goal into venue booking, speaker outreach, and logistics, and checks for scheduling conflicts.

One connector, every AI

Agent Task Decomposition Engine works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

Building your own app? The connector is yours to use.

You don't need a client to put Agent Task Decomposition Engine to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

895ms average. Fast in production.

Agent Task Decomposition Engine is checked daily against the live service.

Daily averagePeak 1010ms

Oct 3Today

Fastest day: 780ms
Slowest day: 1010ms
14-day trend: Improving-11%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 3 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Agent Task Decomposition Engine, so you can see the experience inside your AI.

It does not authenticate your account with Agent Task Decomposition Engine. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

Agent Task Decomposition Engine Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_v4Dy8TTc6YhYZ0YXxilte3cm6yCi43WQr1tyECyJ/mcp

Claude Desktop

Follow the steps below to connect in seconds.

1In Claude Desktop, open Settings → Connectors.
2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
3Click Add and start a new chat — Agent Task Decomposition Engine capabilities are ready to use.

Configuration · claude_desktop_config.jsonCopy

{
  "mcpServers": {
    "agent-task-decomposition-engine-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_v4Dy8TTc6YhYZ0YXxilte3cm6yCi43WQr1tyECyJ/mcp"
    }
  }
}

Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up Agent Task Decomposition Engine in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Agent Task Decomposition Engine owners hand off.

If your job involves managing projects or coordinating complex workflows, this MCP is for you. It lets you build AI agents that don't just guess at the next step; they follow a quantifiable, validated plan. Use this when the success of a task depends on perfect sequencing and logic.

01
Project Manager
Use it to hand off large, multi-phase projects to your agent, ensuring all dependencies are mapped out.
02
Technical Lead
It helps your agent break down software requirements into testable, sequential development tasks.
03
AI Developer
Integrate it into agent orchestration pipelines that require deterministic, verifiable planning logic.

FAQ

Questions Agent Task Decomposition Engine owners ask.

01
Does this MCP just list tasks, or does it create a plan?
It does more than list tasks. It creates a structured, hierarchical plan. It breaks the goal down into subtasks and leaf actions, giving you a true roadmap, not just a checklist.
02
What happens if my plan has a logical error?
You use the validate_dependencies capability. This checks for circular references, which are logical loops. If a loop exists, the MCP flags it, preventing your agent from getting stuck in a planning cycle.
03
Can I use this for non-project goals?
Yes. While it's built for planning, it works on any high-level objective. Whether it's writing a book or planning a trip, it forces the goal into a structured, actionable format.
04
Is the complexity score useful?
The complexity score is a metric that quantifies the difficulty of the task tree. It helps you understand the overall effort required and how many parts can be worked on at the same time.
05
How is task complexity calculated?
Complexity is a weighted sum of word count, domain specificity, and ambiguity, which is then scaled by the decomposition depth.
06
What happens if a task is too ambiguous?
If the ambiguity score exceeds 0.8, the decompose_task capability will flag the task as too vague for reliable decomposition.
07
Can I detect circular dependencies between tasks?
Yes, you can use the validate_dependencies capability to ensure your task hierarchy does not contain logical loops.

Explore

More in Productivity

Connect Agent Task Decomposition Engine to Claude, Cursor, ChatGPT & more

Your AI does the work. We keep it safe and sound.

Each Connector runs inside its own sealed environment.

One switch stops every agent. Instantly.

Spending limits that pause instead of surprise.

We ship only the actions that matter.

01-03

Analyze complexity

Decompose task

Validate dependencies

What teams actually run

Marketing Campaign Planning

Software Development Sprints

Academic Research Project

Event Coordination

Building your own app? The connector is yours to use.

Agent Task Decomposition Engine Connector

Claude Desktop

Project Manager

Technical Lead

AI Developer

Does this MCP just list tasks, or does it create a plan?

What happens if my plan has a logical error?

Can I use this for non-project goals?

Is the complexity score useful?

How is task complexity calculated?

What happens if a task is too ambiguous?

Can I detect circular dependencies between tasks?

GitScrum Tasks AI Connector

Ellie Planner AI Connector

Pond Plant Coverage Planner AI Connector

Markdown Task Extractor AI Connector

Suggestions

Urea Plant Design Engineer AI Connector

Vinyl Chloride Plant Design Engine AI Connector

Well Intervention Planning Engine AI Connector

PVC Plant Design Engineer AI Connector